Ppt Template Creator logo

Ppt Template Creator

OrganizationPopular
anthropics
ppt-template-creator

Creates self-contained PPT template SKILLS (not presentations) from user-provided PowerPoint templates. Use ONLY when a user wants to create a reusable skill from their template. For creating actual presentations, use the pptx skill instead.

Overview

Publisheranthropics
Repositoryfinancial-services
Skill nameppt-template-creator
Stars
38.4K
Forks
5.5K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by anthropics on GitHub. Read the source before you install it.

Installation

Install the Ppt Template Creator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/anthropics/financial-services/tree/main/plugins/vertical-plugins/financial-analysis/skills/ppt-template-creator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/anthropics/financial-services.git /tmp/financial-services
mkdir -p .claude/skills
cp -r /tmp/financial-services/plugins/vertical-plugins/financial-analysis/skills/ppt-template-creator .claude/skills/ppt-template-creator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ppt Template Creator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ppt Template Creator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ppt Template Creator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PPT Template Creator

This skill creates SKILLS, not presentations. Use this when a user wants to turn their PowerPoint template into a reusable skill that can generate presentations later. If the user just wants to create a presentation, use the pptx skill instead.

The generated skill includes:

  • assets/template.pptx - the template file
  • SKILL.md - complete instructions (no reference to this meta skill needed)

For general skill-building best practices, refer to the skill-creator skill. This skill focuses on PPT-specific patterns.

Workflow

  1. User provides template (.pptx or .potx)
  2. Analyze template - extract layouts, placeholders, dimensions
  3. Initialize skill - use the skill-creator skill to set up the skill structure
  4. Add template - copy .pptx to assets/template.pptx
  5. Write SKILL.md - follow template below with PPT-specific details
  6. Create example - generate sample presentation to validate
  7. Package - use the skill-creator skill to package into a .skill file

Step 2: Analyze Template

CRITICAL: Extract precise placeholder positions - this determines content area boundaries.

python
from pptx import Presentation

prs = Presentation(template_path)
print(f"Dimensions: {prs.slide_width/914400:.2f}\" x {prs.slide_height/914400:.2f}\"")
print(f"Layouts: {len(prs.slide_layouts)}")

for idx, layout in enumerate(prs.slide_layouts):
    print(f"\n[{idx}] {layout.name}:")
    for ph in layout.placeholders:
        try:
            ph_idx = ph.placeholder_format.idx
            ph_type = ph.placeholder_format.type
            # IMPORTANT: Extract exact positions in inches
            left = ph.left / 914400
            top = ph.top / 914400
            width = ph.width / 914400
            height = ph.height / 914400
            print(f"    idx={ph_idx}, type={ph_type}")
            print(f"        x={left:.2f}\", y={top:.2f}\", w={width:.2f}\", h={height:.2f}\"")
        except:
            pass

Key measurements to document:

  • Title position: Where does the title placeholder sit?
  • Subtitle/description: Where is the subtitle line?
  • Footer placeholders: Where do footers/sources appear?
  • Content area: The space BETWEEN subtitle and footer is your content area

Finding the True Content Start Position

CRITICAL: The content area does NOT always start immediately after the subtitle placeholder. Many templates have a visual border, line, or reserved space between the subtitle and content area.

Best approach: Look at Layout 2 or similar "content" layouts that have an OBJECT placeholder - this placeholder's y position indicates where content should actually start.

python
# Find the OBJECT placeholder to determine true content start
for idx, layout in enumerate(prs.slide_layouts):
    for ph in layout.placeholders:
        try:
            if ph.placeholder_format.type == 7:  # OBJECT type
                top = ph.top / 914400
                print(f"Layout [{idx}] {layout.name}: OBJECT starts at y={top:.2f}\"")
                # This y value is where your content should start!
        except:
            pass

Example: A template might have:

  • Subtitle ending at y=1.38"
  • But OBJECT placeholder starting at y=1.90"
  • The gap (0.52") is reserved for a border/line - do not place content there

Use the OBJECT placeholder's y position as your content start, not the subtitle's end position.

Step 5: Write SKILL.md

The generated skill should have this structure:

[company]-ppt-template/
├── SKILL.md
└── assets/
    └── template.pptx

Generated SKILL.md Template

The generated SKILL.md must be self-contained with all instructions embedded. Use this template, filling in the bracketed values from your analysis:

markdown
---
name: [company]-ppt-template
description: [Company] PowerPoint template for creating presentations. Use when creating [Company]-branded pitch decks, board materials, or client presentations.
---

# [Company] PPT Template

Template: `assets/template.pptx` ([WIDTH]" x [HEIGHT]", [N] layouts)

## Creating Presentations

```python
from pptx import Presentation

prs = Presentation("path/to/skill/assets/template.pptx")

# DELETE all existing slides first
while len(prs.slides) > 0:
    rId = prs.slides._sldIdLst[0].rId
    prs.part.drop_rel(rId)
    del prs.slides._sldIdLst[0]

# Add slides from layouts
slide = prs.slides.add_slide(prs.slide_layouts[LAYOUT_IDX])
```

## Key Layouts

| Index | Name | Use For |
|-------|------|---------|
| [0] | [Layout Name] | [Cover/title slide] |
| [N] | [Layout Name] | [Content with bullets] |
| [N] | [Layout Name] | [Two-column layout] |

## Placeholder Mapping

**CRITICAL: Include exact positions (x, y coordinates) for each placeholder.**

### Layout [N]: [Name]
| idx | Type | Position | Use |
|-----|------|----------|-----|
| [idx] | TITLE (1) | y=[Y]" | Slide title |
| [idx] | BODY (2) | y=[Y]" | Subtitle/description |
| [idx] | BODY (2) | y=[Y]" | Footer |
| [idx] | BODY (2) | y=[Y]" | Source/notes |

### Content Area Boundaries

**Document the safe content area for custom shapes/tables/charts:**

```
Content Area (for Layout [N]):
- Left margin: [X]" (content starts here)
- Top: [Y]" (below subtitle placeholder)
- Width: [W]"
- Height: [H]" (ends before footer)

For 4-quadrant layouts:
- Left column: x=[X]", width=[W]"
- Right column: x=[X]", width=[W]"
- Top row: y=[Y]", height=[H]"
- Bottom row: y=[Y]", height=[H]"
```

**Why this matters:** Custom content (textboxes, tables, charts) must stay within these boundaries to avoid overlapping with template placeholders like titles, footers, and source lines.

## Filling Content

**Do NOT add manual bullet characters** - slide master handles formatting.

```python
# Fill title
for shape in slide.shapes:
    if hasattr(shape, 'placeholder_format'):
        if shape.placeholder_format.type == 1:  # TITLE
            shape.text = "Slide Title"

# Fill content with hierarchy (level 0 = header, level 1 = bullet)
for shape in slide.shapes:
    if hasattr(shape, 'placeholder_format'):
        idx = shape.placeholder_format.idx
        if idx == [CONTENT_IDX]:
            tf = shape.text_frame
            for para in tf.paragraphs:
                para.clear()

            content = [
                ("Section Header", 0),
                ("First bullet point", 1),
                ("Second bullet point", 1),
            ]

            tf.paragraphs[0].text = content[0][0]
            tf.paragraphs[0].level = content[0][1]
            for text, level in content[1:]:
                p = tf.add_paragraph()
                p.text = text
                p.level = level
```

## Example: Cover Slide

```python
slide = prs.slides.add_slide(prs.slide_layouts[[COVER_IDX]])
for shape in slide.shapes:
    if hasattr(shape, 'placeholder_format'):
        idx = shape.placeholder_format.idx
        if idx == [TITLE_IDX]:
            shape.text = "Company Name"
        elif idx == [SUBTITLE_IDX]:
            shape.text = "Presentation Title | Date"
```

## Example: Content Slide

```python
slide = prs.slides.add_slide(prs.slide_layouts[[CONTENT_IDX]])
for shape in slide.shapes:
    if hasattr(shape, 'placeholder_format'):
        ph_type = shape.placeholder_format.type
        idx = shape.placeholder_format.idx
        if ph_type == 1:
            shape.text = "Executive Summary"
        elif idx == [BODY_IDX]:
            tf = shape.text_frame
            for para in tf.paragraphs:
                para.clear()
            content = [
                ("Key Findings", 0),
                ("Revenue grew 40% YoY to $50M", 1),
                ("Expanded to 3 new markets", 1),
                ("Recommendation", 0),
                ("Proceed with strategic initiative", 1),
            ]
            tf.paragraphs[0].text = content[0][0]
            tf.paragraphs[0].level = content[0][1]
            for text, level in content[1:]:
                p = tf.add_paragraph()
                p.text = text
                p.level = level
```

Step 6: Create Example Output

Generate a sample presentation to validate the skill works. Save it alongside the skill for reference.

PPT-Specific Rules for Generated Skills

  1. Template in assets/ - always bundle the .pptx file
  2. Self-contained SKILL.md - all instructions embedded, no external references
  3. No manual bullets - use paragraph.level for hierarchy
  4. Delete slides first - always clear existing slides before adding new ones
  5. Document placeholders by idx - placeholder idx values are template-specific

Frequently asked questions

What does the Ppt Template Creator AI skill do?

Creates self-contained PPT template SKILLS (not presentations) from user-provided PowerPoint templates. Use ONLY when a user wants to create a reusable skill from their template. For creating actual presentations, use the pptx skill instead.

Why use Ppt Template Creator on TypingMind?

Because you install it once and use it with any model. Ppt Template Creator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ppt Template Creator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anthropics/financial-services/tree/main/plugins/vertical-plugins/financial-analysis/skills/ppt-template-creator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ppt Template Creator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ppt Template Creator?

As many as you like. As long as a model supports skills, you can use Ppt Template Creator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ppt Template Creator AI skill free?

Yes. It is published on GitHub by anthropics under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇